RNA expression analysis of Brassica Microbe Data. I: prep data

Data is from August, 2017 sequencing. This is week 4 of experiment 1

Download and map:

Working on Whitney for read mapping. Directory: /Network/Servers/avalanche.plb.ucdavis.edu/Volumes/Mammoth/Users/jmaloof/2017/Wyoming-microbiome/20170830-data/

20170830 reads

Build index (not done…already exists)

cd ~/Sequences/ref_genomes/B_rapa/genome/V3.0

wget http://brassicadb.org/brad/datasets/pub/BrassicaceaeGenome/Brassica_rapa/V3.0/Brapa_genome_v3.0_cds.fasta.gz 

kallisto index -i B_rapa_CDS_V3.0_k31_kallisto_index Brapa_genome_v3.0_cds.fasta.gz

cd ~/2017/Wyoming-microbiome//20170830-samples/20170830-data

Map reads

mkdir kallisto_out_V3.0

#actually a fish loop
for file in (ls raw-fastq/2017-08-27/*.fastq.gz)
  echo $file
  set newfile (basename $file _R1_001.fastq.gz)
  kallisto quant -i ~/Sequences/ref_genomes/B_rapa/genome/V3.0/B_rapa_CDS_V3.0_k31_kallisto_index  -o kallisto_out_V3.0/$newfile --single -l 200 -s 40 -t 4 --plaintext $file
end

Move the counts to my local computer

cd /Users/jmaloof/git/Br_Microbe_Paper_2021/RNA/input/20170830-samples
lftp sftp://whitney.plb.ucdavis.edu
  cd 2017/Wyoming-microbiome/20170830-samples/20170830-data
  mirror kallisto_out_V3.0

remove unused files

cd /Users/jmaloof/git/Br_Microbe_Paper_2021/RNA/input/20170830-samples/kallisto_out_V3.0
rm */*.json

compress tsv files

cd /Users/jmaloof/git/Br_Microbe_Paper_2021/RNA/input/20170830-samples/kallisto_out_V3.0
gzip */abundance.tsv

Get counts into R

library(tidyverse)
library(stringr)
library(edgeR)

kallisto_files <- dir(path = "../../input/20170830-samples/kallisto_out_V3.0",pattern="abundance.tsv",recursive = TRUE,full.names = TRUE)
kallisto_names <- str_split(kallisto_files,"/",simplify=TRUE)[,6]
head(kallisto_names)

[1] "wyo_leaf_R500_10_417_S65_L001" "wyo_leaf_R500_10_417_S65_L002" "wyo_leaf_R500_10_417_S65_L003"
[4] "wyo_leaf_R500_10_417_S65_L004" "wyo_leaf_R500_10_419_S66_L001" "wyo_leaf_R500_10_419_S66_L002"

counts <- tibble(sample = kallisto_names, file = kallisto_files) %>%
  mutate(countdata = map(kallisto_files, read_tsv)) %>%
  select(-file)

── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)


── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  target_id = col_character(),
  length = col_double(),
  eff_length = col_double(),
  est_counts = col_double(),
  tpm = col_double()
)

head(counts)

reformat into rows = genes and columns = samples

counts <- counts %>% unnest(countdata) %>%
  mutate(sample = str_remove(sample, "_L.*")) %>% 
  select(sample, target_id, est_counts) %>%
  group_by(sample, target_id) %>%
  summarize(est_counts=sum(est_counts)) %>% # sum up counts from multiple lanes
  ungroup() %>%
  pivot_wider(id_cols = target_id,
              names_from = sample,
              values_from = est_counts)

`summarise()` has grouped output by 'sample'. You can override using the `.groups` argument.

head(counts)

dim(counts)

[1] 46250    25

write_csv(counts,"../../output/20170830_V3.0_raw_counts_.csv.gz")

make sample description data frame

summarize counts

pl.orig <- counts[,-1] %>% colSums() %>% tibble(sample=names(.),count=.) %>%
  ggplot(aes(x=sample,y=count)) + 
  geom_col() +
  theme(axis.text.x  = element_text(angle=90, vjust=0.5,size = 7)) 
pl.orig

load to edgeR, normalize

#confirm that everthing is in the right order
all(colnames(counts)[-1]==sample.description$sample)

[1] TRUE

dge <- DGEList(counts[,-1],
               group=sample.description$group,
               samples=sample.description,
               genes=counts$target_id)

dge <- calcNormFactors(dge)
barplot(dge$samples$lib.size)

ggplot(dge$samples,aes(x=sample,y=norm.factors,fill=tissue)) + geom_col() + 
  theme(axis.text.x  = element_text(angle=90, vjust=0.5,size = 7)) 

ggplot(dge$samples,aes(x=sample,y=norm.factors,fill=genotype)) + geom_col() + 
  theme(axis.text.x  = element_text(angle=90, vjust=0.5,size = 7)) 

ggplot(dge$samples,aes(x=sample,y=norm.factors,fill=as.factor(block))) + geom_col() +
  theme(axis.text.x  = element_text(angle=90, vjust=0.5,size = 7)) 

do separately for leaf and root values

counts.leaf <- counts %>% select(target_id, contains("leaf"))
counts.root <- counts %>% select(target_id, contains("root"))
sample.description.leaf <- sample.description %>% filter(tissue=="leaf")
sample.description.root <- sample.description %>% filter(tissue=="root")

Leaf

#confirm that everthing is in the right order
all(colnames(counts.leaf)[-1]==sample.description.leaf$sample)

[1] TRUE

dge.leaf <- DGEList(counts.leaf[,-1],
                    group=sample.description.leaf$group,
                    samples=sample.description.leaf,
                    genes=counts.leaf$target_id)
dge.leaf <- calcNormFactors(dge.leaf)

Root

#confirm that everthing is in the right order
all(colnames(counts.root)[-1]==sample.description.root$sample)

[1] TRUE

dge.root <- DGEList(counts.root[,-1],
                    group=sample.description.root$group,
                    samples=sample.description.root,
                    genes=counts.root$target_id)
dge.root <- calcNormFactors(dge.root)

save(dge.leaf,dge.root,sample.description.leaf,sample.description.root,file="../../output/edgeR_dge_objects_exp1_week4.Rdata")

Write out cpm values

cpm.leaf.w <- bind_cols(dge.leaf$gene,as_tibble(cpm(dge.leaf))) %>% as_tibble() %>% rename(transcript_ID=genes)
head(cpm.leaf.w)

write_csv(cpm.leaf.w,"../../output/cpm_wide_exp1_week4_leaf_samples.csv.gz")

cpm.root.w <- bind_cols(dge.root$gene,as_tibble(cpm(dge.root))) %>% as_tibble() %>% rename(transcript_ID=genes)
head(cpm.root.w)

write_csv(cpm.root.w,"../../output/cpm_wide_exp1_week4_root_samples.csv.gz")

Also let’s reformat this to long format and add metadata

cpm.leaf.long <- cpm.leaf.w %>% 
  gather(-transcript_ID,key = sample,value=cpm) %>%
  left_join(sample.description.leaf)

Joining, by = "sample"

head(cpm.leaf.long)

write_csv(cpm.leaf.long,"../../output/cpm_long_with_metadata_exp1_week4_leaf_samples.csv.gz")

cpm.root.long <- cpm.root.w %>% 
  gather(-transcript_ID,key = sample,value=cpm) %>%
  left_join(sample.description.root)

Joining, by = "sample"

head(cpm.root.long)

write_csv(cpm.root.long,"../../output/cpm_long_with_metadata_exp1_week4_root_samples.csv.gz")

compute and write out voom-transformed values

design.leaf <- model.matrix(~ sample.description.leaf$group)
dge4voom.leaf <- dge.leaf[rowSums(cpm(dge.leaf)>1) >= 6,,keep.lib.sizes=FALSE]
dge4voom.leaf <- calcNormFactors(dge4voom.leaf)
data.voom.leaf <- voom(dge4voom.leaf,design = design.leaf)
data.voom.exp.leaf <- bind_cols(data.voom.leaf$genes,as_tibble(data.voom.leaf$E)) %>%
  rename(transcript_ID=genes) %>% as_tibble()
head(data.voom.exp.leaf)

write_csv(data.voom.exp.leaf, "../../output/voom_expression_exp1_week4_T6_leaf_samples.csv.gz")

voom.long.leaf <- data.voom.exp.leaf %>% 
  gather(-transcript_ID,key = sample,value=expression) %>%
  left_join(sample.description.leaf)

Joining, by = "sample"

head(voom.long.leaf)

hist(voom.long.leaf$expression)

write_csv(voom.long.leaf,"../../output/voom_long_with_metadata_exp1_week4_T6_leaf_samples.csv.gz")

design.root <- model.matrix(~ sample.description.root$group)
dge4voom.root <- dge.root[rowSums(cpm(dge.root)>1) >= 6,,keep.lib.sizes=FALSE]
dge4voom.root <- calcNormFactors(dge4voom.root)
data.voom.root <- voom(dge4voom.root,design = design.root)
data.voom.exp.root <- bind_cols(data.voom.root$genes,as_tibble(data.voom.root$E)) %>%
  rename(transcript_ID=genes) %>% as_tibble()
head(data.voom.exp.root)

write_csv(data.voom.exp.root, "../../output/voom_expression_exp1_week4_T6_root_samples.csv.gz")

voom.long.root <- data.voom.exp.root %>% 
  gather(-transcript_ID,key = sample,value=expression) %>%
  left_join(sample.description.root)

Joining, by = "sample"

head(voom.long.root)

hist(voom.long.root$expression)

write_csv(voom.long.root,"../../output/voom_long_with_metadata_exp1_week4_T6_root_samples.csv.gz")